Skip to content
conftrace_

attack defense

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

poison training (1) poisoned training (1) risky prompt detection (1) trigger word (1) generative model safety (1) trigger injection (1) safety evaluation (1) text-to-image model (1) diffusion model (1) backdoor attack (1)

Papers

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model AAAI 2026 BITE: Textual Backdoor Attacks with Iterative Trigger Injection ACL 2023